{"id":"https://openalex.org/W4294961189","doi":"https://doi.org/10.48550/arxiv.2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","display_name":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4294961189","doi":"https://doi.org/10.48550/arxiv.2209.02242"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.02242","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.02242","pdf_url":"https://arxiv.org/pdf/2209.02242","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.02242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100452641","display_name":"Han Wang","orcid":"https://orcid.org/0000-0001-5448-9903"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633673","display_name":"Jun Tang","orcid":"https://orcid.org/0000-0002-5470-8798"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374771","display_name":"Xiaodong Liu","orcid":"https://orcid.org/0000-0001-8652-9818"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaodong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070466381","display_name":"Shanyan Guan","orcid":"https://orcid.org/0000-0003-0875-167X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Shanyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026237422","display_name":"Rong Xie","orcid":"https://orcid.org/0009-0006-6092-328X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Rong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100448208","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-7961-8502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100452641"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.783454179763794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5579158663749695},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5376044511795044},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5361974239349365},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.520566999912262},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48539623618125916},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.482090026140213},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.477020263671875},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.44175460934638977},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4415563642978668},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43112242221832275},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.42338934540748596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2976417541503906},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1233167052268982},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.10155734419822693},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08739632368087769},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08562389016151428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783454179763794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5579158663749695},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5376044511795044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5361974239349365},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.520566999912262},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48539623618125916},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.482090026140213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.477020263671875},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.44175460934638977},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4415563642978668},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43112242221832275},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.42338934540748596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2976417541503906},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1233167052268982},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.10155734419822693},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08739632368087769},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08562389016151428},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.02242","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.02242","pdf_url":"https://arxiv.org/pdf/2209.02242","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.02242","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.02242","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.02242","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.02242","pdf_url":"https://arxiv.org/pdf/2209.02242","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3148227991","https://openalex.org/W1486593826","https://openalex.org/W2771174107","https://openalex.org/W1536965844","https://openalex.org/W4310880131","https://openalex.org/W2344941099","https://openalex.org/W4322212724","https://openalex.org/W2106788855","https://openalex.org/W3081561710","https://openalex.org/W2477413883"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"a":[4,55,104,125],"trend":[5],"of":[6,14],"applying":[7],"context":[8,89,118],"frames":[9,42,90],"to":[10,29,58,98,110,136],"boost":[11],"the":[12,31,51,76,88,92,96,112,146],"performance":[13],"object":[15,19],"detection":[16],"as":[17],"video":[18],"detection.":[20],"Existing":[21],"methods":[22],"usually":[23,36],"aggregate":[24],"features":[25],"at":[26,153],"one":[27],"stroke":[28],"enhance":[30],"feature.":[32],"These":[33],"methods,":[34],"however,":[35],"lack":[37],"spatial":[38,64],"information":[39,62,65,72,115],"from":[40,45],"neighboring":[41],"and":[43,63,91,120],"suffer":[44],"insufficient":[46],"feature":[47,78],"aggregation.":[48],"To":[49],"address":[50],"issues,":[52],"we":[53,102],"perform":[54],"progressive":[56],"way":[57],"introduce":[59],"both":[60],"temporal":[61,71,77],"for":[66],"an":[67,84,133],"integrated":[68],"enhancement.":[69],"The":[70],"is":[73],"introduced":[74],"by":[75,82],"aggregation":[79],"model":[80],"(TFAM),":[81],"conducting":[83],"attention":[85],"mechanism":[86],"between":[87,116],"target":[93,121],"frame":[94,97,119],"(i.e.,":[95],"be":[99],"detected).":[100],"Meanwhile,":[101],"employ":[103],"Spatial":[105],"Transition":[106],"Awareness":[107],"Model":[108],"(STAM)":[109],"convey":[111],"location":[113],"transition":[114],"each":[117],"frame.":[122],"Built":[123],"upon":[124],"transformer-based":[126],"detector":[127],"DETR,":[128],"our":[129],"PTSEFormer":[130],"also":[131],"follows":[132],"end-to-end":[134],"fashion":[135],"avoid":[137],"heavy":[138],"post-processing":[139],"procedures":[140],"while":[141],"achieving":[142],"88.1%":[143],"mAP":[144],"on":[145],"ImageNet":[147],"VID":[148],"dataset.":[149],"Codes":[150],"are":[151],"available":[152],"https://github.com/Hon-Wong/PTSEFormer.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}